AI 模型库
multilingual-e5-base
sentence-similarity多语言E5文本嵌入：技术报告。 王亮，杨楠，黄小龙，杨林军，Rangan Majumder，韦福如，arXiv 2024
bert-base-cased
fill-mask基于掩码语言建模（MLM）目标在英语上预训练的模型。该模型首次发表于此论文，并在此仓库中首次发布。本模型区分大小写：例如，它能够区分"english"和"English"。
wav2vec2-large-xlsr-53-russian
automatic-speech-recognitionFine-tuned XLSR-53 large model for speech recognition in Russian
Qwen2-VL-2B-Instruct
image-text-to-textWe're excited to unveil **Qwen2-VL**, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
chronos-bolt-base
time-series-forecasting🚀 **Update Feb 14, 2025**: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lin
Mistral-7B-Instruct-v0.3
Mistral-7B-Instruct-v0.3大型语言模型（LLM）是Mistral-7B-v0.3的指令微调版本。
bert-base-multilingual-uncased
fill-mask基于掩码语言建模（MLM）目标，在维基百科规模最大的前102种语言上预训练的模型。该模型首次发表于此论文，并在此仓库中首次发布。此模型不区分大小写：对"english"和"English"不作区分。
bge-reranker-base
text-classification**我们已更新了新的重排序器，支持更长的序列长度、更多语言，并实现了更优的性能。**
DeepSeek-R1
text-generationDeepSeek-R1 <!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable html --> <!-- markdownlint-disable no-duplicate-header -->
Qwen3.6-35B-A3B
image-text-to-text> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Tra
all-MiniLM-L6-v2
feature-extractionhttps://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 附带 ONNX 权重，以兼容 Transformers.js。
Wan_2.1_ComfyUI_repackaged
Wan 2.1 已重新打包，适用于 ComfyUI。示例请参见：https://comfyanonymous.github.io/ComfyUI_examples/wan
voice-activity-detection
automatic-speech-recognition自动语音识别
Qwen3-4B
text-generationQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groun
Qwen3.6-35B-A3B-FP8
image-text-to-text> [!Note] > This repository contains FP8-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hu
paraphrase-MiniLM-L6-v2
sentence-similarity这是一个sentence-transformers模型：它将句子和段落映射到384维的稠密向量空间，可用于聚类或语义搜索等任务。
distilbert-base-uncased-finetuned-sst-2-english
text-classification目录 - 模型详情 - 模型入门指南 - 用途 - 风险、局限性与偏见 - 训练
mms-300m-1130-forced-aligner
automatic-speech-recognitionForced Alignment with Hugging Face CTC Models This Python package provides an efficient way to perform forced alignment between text and audio using Hugging Face's pretrained models. it also features
wav2vec2-large-xlsr-53-portuguese
automatic-speech-recognitionFine-tuned XLSR-53 large model for speech recognition in Portuguese
Qwen3.5-35B-A3B
image-text-to-text> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Tra